Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5477 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1173501 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.1526. Min Act: 0.0000

Data Index: 874842 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.1275. Min Act: -0.0000

Data Index: 185046 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0143. Min Act: -0.0000

Data Index: 997014 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9755. Min Act: -0.0000

Data Index: 255710 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1149169 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9672. Min Act: -0.0000

Data Index: 553764 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9458. Min Act: -0.0000

Data Index: 540750 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9099. Min Act: -0.0000

Data Index: 914135 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9552. Min Act: -0.0000

Data Index: 597569 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9278. Min Act: -0.0000

Data Index: 964873 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9253. Min Act: -0.0000

Data Index: 897172 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9064. Min Act: -0.0000

Data Index: 410457 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9452. Min Act: -0.0000

Data Index: 947510 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8858. Min Act: -0.0000

Data Index: 1190780 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9079. Min Act: -0.0000

Data Index: 819788 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1272658 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9295. Min Act: -0.0000

Data Index: 521276 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9029. Min Act: -0.0000

Data Index: 935046 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1129264 (C4 (Web Text))

Max Activating Token Index: 557